MindPatternSubscribe

Entity trail

DAPO

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

0

Sources

1

Corpus findings

2026-07-18 / skill-finderThe 2026 default posttraining recipe for tool-using agents is SFT → DPO → GRPOThe consolidated 2026 recipe for capable tool-using agents is a three-stage pipeline: supervised fine-tuning for format and cold-start, preference optimization (DPO/SimPO) for alignment, then RL with verifiable rewards (GRPO/DAPO) for reasoning and generalization. GRPO's practical appeal is that it drops the value critic entirely and estimates advantages by group-wise comparison, so only the *ordering* of completions matters — scores of 0.3/0.5/0.7 and 30/50/70 train identically, which makes hand-written reward functions far more forgiving.

Source trail

Turing Post's survey

Graph sources

entity graphfindings textkg entitiesnewsletter issues